hugpadhugpad

trohrbaugh / LFM2-24B-A2B-heretic-ara

Text Generation24B512Updated Apr 14, 2026
Hugging Face

Downloads

51

Likes

2

Last updated

Apr 14, 2026

License

lfm1.0

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • lfm2_moe
  • text-generation
  • liquid
  • lfm2
  • edge

Technical specifications

Parameters24B
Librarytransformers
Languages9 languages
Licenselfm1.0